Kosha Model Discovery
Tells your agent which model to use and what it costs, across 46 providers and local runtimes.
Servidor MCP · de sriinnu
Resumo
Kosha Model Discovery é um servidor MCP publicado por sriinnu. Marketplaces que lemos e que o listam: 1 (Official MCP Registry). Vimos pela primeira vez em 2026-10-11 e não registramos mudanças desde então. Conforme nossa passagem pelos marketplaces em 2026-10-14.
O que pede
- Roda na sua máquina
- Segredos: 6
- Configurações: 7
Exige: ANTHROPIC_API_KEY (secreta), GOOGLE_API_KEY (secreta), OPENAI_API_KEY (secreta), OPENROUTER_API_KEY (secreta), TYPESAFE_API_KEY (secreta), XAI_API_KEY (secreta)
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Pacote
npm @sriinnu/kosha-discovery (@sriinnu/kosha-discovery no npm)
- Downloads do npm por semana: 388 (2026-10-12)
- Downloads do npm por mês: 2 134 (2026-10-12)
- Última versão no npm: 1.8.1, publicada em 2026-10-06
Nenhuma vulnerabilidade conhecida no OSV para 1.8.1 (verificado em 2026-10-13)
Os dados do npm vêm do registro público do npm (registry.npmjs.org, api.npmjs.org). Cada número é do próprio registro e nunca é somado a outro. Um registro que não publica um número não mostra nenhum: sem número não é zero. Os registros de vulnerabilidades vêm do OSV.dev (CC BY 4.0) e dizem respeito apenas à versão declarada; uma listagem sem versão declarada não recebe resposta. Não analisamos código.
Funciona com
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como servidor MCP local: pacote npm
Gerado a partir do que Official MCP Registry declara.
claude mcp add --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "GOOGLE_API_KEY=<YOUR_GOOGLE_API_KEY>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>" --env "XAI_API_KEY=<YOUR_XAI_API_KEY>" --transport stdio kosha-discovery -- npx -y @sriinnu/kosha-discovery[mcp_servers.kosha-discovery]
command = "npx"
args = ["-y", "@sriinnu/kosha-discovery"]
[mcp_servers.kosha-discovery.env]
ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>"
GOOGLE_API_KEY = "<YOUR_GOOGLE_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
OPENROUTER_API_KEY = "<YOUR_OPENROUTER_API_KEY>"
TYPESAFE_API_KEY = "<YOUR_TYPESAFE_API_KEY>"
XAI_API_KEY = "<YOUR_XAI_API_KEY>"{
"mcpServers": {
"kosha-discovery": {
"command": "npx",
"args": [
"-y",
"@sriinnu/kosha-discovery"
],
"env": {
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GOOGLE_API_KEY": "<YOUR_GOOGLE_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>",
"XAI_API_KEY": "<YOUR_XAI_API_KEY>"
}
}
}
}Substitua os valores entre sinais de menor e maior pelos seus. Mostramos os nomes das configurações, nunca valores.
Configurações opcionais que também indica: KOSHA_CACHE_TTL_HOURS.
Onde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Official MCP Registry (Abrir o registro) | Listado | 1.8.1 | Downloads por mês (npm): 2 134 Downloads por semana (npm): 388 Forks (GitHub): 0 Estrelas (GitHub): 2 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
O que mudou
Nada mudou neste plugin desde que começamos a acompanhá-lo.
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
modelglass io.github.Modelglass/modelglass
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
-
Live registry of AI model specs, context windows, and per-token pricing.
-
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
-
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
-
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
-
ToolDrift: Current AI model pricing and which models coding tools route to.
-
modelcostsaver io.github.sachinuppal/modelcostsaver
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.
-
AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.
-
LLM provider intelligence: recommendations, pricing, and status
-
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
together-ai-skills
A collection of skills that teach coding agents how to use the Together AI platform, including chat completions, image generation, video, audio, embeddings, fine-tuning, batch…
-
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Listado em Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
Listado em Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
Listado em Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
Listado em Community GitHub marketplaces (5)
-
Accurate API model IDs, pricing, and specs for 46 models across 7 AI providers.
-
agentcents io.github.labham-llc/agentcents
Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.
-
Connect Codex to a self-hosted AI gateway with provider-free prompt enhancement and fifteen governed MCP tools.
-
Tuning Engines - Governed AI Runtime
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
-
The Weckr cost and margin toolkit for your AI assistant: integrate the SDK, look up current LLM token prices, estimate what an AI feature costs per user before you ship, and audit…
Listado em Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
-
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform…
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
Listado em Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
-
mobile-app
Build and deploy Power Apps code apps for mobile using Expo (React Native), with native device functionality and Power Platform connectors
Listado em Cursor: cursor/plugins (5)
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Let Grok Bot reach MCP servers on your private Tailscale network. Sign in to Tailscale to connect your tailnet; Grok Bot joins it as one tagged device and only reaches the hosts…
Listado em Docker MCP Catalog (5)
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Seamless interaction with Novita AI platform resources.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
Listado em Official MCP Registry (5)
-
modelglass io.github.Modelglass/modelglass
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
-
Live registry of AI model specs, context windows, and per-token pricing.
-
ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them.
-
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
-
One key, every model: measured scores and live prices, routed per request to the cheapest fit.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Este plugin é seu?
Adicione-o aos seus projetos e prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS. Você recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Official MCP Registry. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.